Citation Chaining

SkillMonitoring & ops

Forward and backward citation tracing tactic — expand paper coverage

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Citation Chaining skill

What this skill tells your AI

The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/citation-chaining/SKILL.md and read by ahel’s review.

Expand paper coverage by tracing citation networks in both directions.

Operations

  • Backward chaining: ss_references — what does this paper cite?
  • Forward chaining: ss_citations — what cites this paper?

Available SOPs

  • paper-overview (import) — quick scan of discovered papers
  • paper-search (import) — AI summary of promising papers
  • paper-research (import) — deep reading of key papers
  • saturation-detection (subagent) — determine when to stop

Execution Guidance

  • Start from seed/key papers
  • Alternate forward and backward passes
  • After each pass: filter by relevance, add to reading queue
  • Use saturation-detection to stop when new papers aren't adding information
  • Track the chain: paper A → cites B → cites C (provenance)
  • Deduplicate across passes — same paper may appear in multiple chains

Available SOPs

Optional, no fixed order; the final leaf is always a sop.

SOPWhen to use
knowledge-acquisition-paper-overviewAbstract-level paper scanning for broad coverage. Import of literature-engine/literature-overview skill. Abstract-level only — no methodology conclusions from abstracts.
knowledge-acquisition-paper-researchFull-depth paper reading with raw text extraction. Import of literature-engine/literature-research skill. Must read fullText (true) — equations, hyperparameters, specific claims extracted.
knowledge-acquisition-paper-searchAI-summarized paper reading for intermediate depth. Import of literature-engine/literature-search skill. Must call get_paper_content for every analyzed paper.
knowledge-acquisition-saturation-detectionDetermine when additional searching yields diminishing returns. Analyzes the latest expansion batch against existing corpus to judge continue/near-saturation/saturated. Used by snowball and systematic-survey.

Signals

GitHub stars
469
Forks
37
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
citation-chaining
Source
github.com/yogsoth-ai/de-anthropocentric-research-engine